Uncertainty and Prediction Quality Estimation for Semantic Segmentation via Graph Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Heinert, Edgar, Tilgner, Stephan, Palm, Timo, Rottmann, Matthias
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912031980912640
author Heinert, Edgar
Tilgner, Stephan
Palm, Timo
Rottmann, Matthias
author_facet Heinert, Edgar
Tilgner, Stephan
Palm, Timo
Rottmann, Matthias
contents When employing deep neural networks (DNNs) for semantic segmentation in safety-critical applications like automotive perception or medical imaging, it is important to estimate their performance at runtime, e.g. via uncertainty estimates or prediction quality estimates. Previous works mostly performed uncertainty estimation on pixel-level. In a line of research, a connected-component-wise (segment-wise) perspective was taken, approaching uncertainty estimation on an object-level by performing so-called meta classification and regression to estimate uncertainty and prediction quality, respectively. In those works, each predicted segment is considered individually to estimate its uncertainty or prediction quality. However, the neighboring segments may provide additional hints on whether a given predicted segment is of high quality, which we study in the present work. On the basis of uncertainty indicating metrics on segment-level, we use graph neural networks (GNNs) to model the relationship of a given segment's quality as a function of the given segment's metrics as well as those of its neighboring segments. We compare different GNN architectures and achieve a notable performance improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2409_11373
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Uncertainty and Prediction Quality Estimation for Semantic Segmentation via Graph Neural Networks
Heinert, Edgar
Tilgner, Stephan
Palm, Timo
Rottmann, Matthias
Computer Vision and Pattern Recognition
68T07
When employing deep neural networks (DNNs) for semantic segmentation in safety-critical applications like automotive perception or medical imaging, it is important to estimate their performance at runtime, e.g. via uncertainty estimates or prediction quality estimates. Previous works mostly performed uncertainty estimation on pixel-level. In a line of research, a connected-component-wise (segment-wise) perspective was taken, approaching uncertainty estimation on an object-level by performing so-called meta classification and regression to estimate uncertainty and prediction quality, respectively. In those works, each predicted segment is considered individually to estimate its uncertainty or prediction quality. However, the neighboring segments may provide additional hints on whether a given predicted segment is of high quality, which we study in the present work. On the basis of uncertainty indicating metrics on segment-level, we use graph neural networks (GNNs) to model the relationship of a given segment's quality as a function of the given segment's metrics as well as those of its neighboring segments. We compare different GNN architectures and achieve a notable performance improvement.
title Uncertainty and Prediction Quality Estimation for Semantic Segmentation via Graph Neural Networks
topic Computer Vision and Pattern Recognition
68T07
url https://arxiv.org/abs/2409.11373